Method for converting two-dimensional video into three-dimensional video automatically

Abstract

The invention provides a method for converting a two-dimensional video into a three-dimensional video automatically. The method comprises the following steps of: firstly, performing Gauss modeling on the background of a static scene with a mobile object to reestablish a static background and segment an approximate foreground region out; secondly, performing geometrical classification on each pixel of a background image by using monocular geometrical information and a classifying studying algorithm and obtaining a depth map according to a classification result; segmenting the image of the foreground region by using a mean shift algorithm; performing edge detection, edge connection and endpoint elimination on the image to obtain a precise foreground region; and fusing the precise foregroundregion with the depth map of the background to obtain the depth map of each frame. The synthesis algorithm of a right view comprises the steps of first reestablishing the background in the right viewand then repairing holes by using the right view background. By the method, the obtained left and right views are projected on three-dimensional display equipment, so that an excellent three dimensional (3D) effect can be automatically achieved and the manpower is not required.

Description

technical field [0001] The invention relates to an automatic conversion technology for two-dimensional video to three-dimensional video, and belongs to the technical field of video and multimedia signal processing. Background technique [0002] 3D video can enable users to enjoy the real 3D feeling, and has become a research hotspot in recent years. But in the application at the present stage, there is a shortage of 3D video sources, and now the main 3D film sources are only 3D movies, and the production cycle of 3D film sources is long and expensive, which limits the development of the 3D TV industry. Considering the large amount of existing two-dimensional video resources, converting two-dimensional video to three-dimensional video can make up for the shortage of three-dimensional film sources on the one hand, and on the other hand, it also enables people to revisit the previous classic two-dimensional video in three-dimensional form. Therefore, converting two-dimensional...

AI Technical Summary

Problems solved by technology

Although the algorithm is simple, the estimated depth value is not accurate enough, and the quality of the synthesized right view is not high

[0005] In addition to the above algorithms, there are also methods that manually extract image objects, and then allocate the depth of each object in the image to obtain a 3D effect. Although this algorithm is accurate in depth allocation, manual participation makes it difficult to automate the algorithm.

Images